Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Documentation of Nursing Diagnosis01:10

Documentation of Nursing Diagnosis

1.3K
The nurse documents nursing diagnoses and enters them into the patient record. The identified patient's nursing diagnosis is either written out with a plan of care or entered into the electronic health record.
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
1.3K
Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

7.4K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
7.4K
Introduction to Special Senses01:26

Introduction to Special Senses

6.2K
Sensory receptors play an integral part in comprehending our external and internal environments. They receive diverse stimuli, converting them into the nervous system's electrochemical signals. This conversion occurs as the stimulus alters the sensory neuron's cell membrane potential, instigating the generation of an action potential. This action potential is subsequently transmitted to the central nervous system (CNS), which integrates with other sensory data or higher cognitive...
6.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Reply.

Journal of the American College of Radiology : JACR·2026
Same author

The Impact of Patient-Provider Relationships on Prostate Cancer Screening: A Cross-Sectional Analysis of the All of Us Research Program.

Urology practice·2026
Same author

Neutrophil-to-lymphocyte ratio in patients with low-flow aortic stenosis undergoing transcatheter aortic valve implantation.

Journal of cardiology·2026
Same author

Discrepancy Between Global-Specific and Disease-Specific Outcome Measures Following Cervical Spine Surgery.

Clinical spine surgery·2026
Same author

Cemiplimab Plus Chemotherapy Versus Chemotherapy in Advanced NSCLC: 5-year Results From Phase 3 EMPOWER-Lung 3 Part 2 Trial.

Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer·2026
Same author

L-TGVN: Leveraging Longitudinal Priors for Personalized Rapid MRI.

ArXiv·2026

Related Experiment Video

Updated: Sep 25, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K

Differences between human and machine perception in medical diagnosis.

Taro Makino1,2, Stanisław Jastrzębski3,4,5, Witold Oleszkiewicz6

  • 1Center for Data Science, New York University, New York, NY, USA. taro@nyu.edu.

Scientific Reports
|April 28, 2022
PubMed
Summary
This summary is machine-generated.

Deep neural networks (DNNs) show promise in medical diagnosis but may fail unexpectedly. A new framework reveals DNNs use different features than humans for breast cancer screening, particularly for soft tissue lesions.

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Related Experiment Videos

Last Updated: Sep 25, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Area of Science:

  • Medical Imaging Analysis
  • Artificial Intelligence in Healthcare
  • Radiology and Diagnostic Imaging

Background:

  • Deep neural networks (DNNs) offer potential for image-based medical diagnosis but can exhibit unreliability due to superficial feature reliance.
  • Human diagnosticians typically utilize features grounded in medical science, making them less prone to such errors.
  • Understanding the differences in feature perception between humans and DNNs is crucial for trustworthy AI in medicine.

Purpose of the Study:

  • To propose and demonstrate a framework for comparing human and machine perception in medical diagnosis.
  • To investigate whether deep neural networks (DNNs) utilize the same diagnostic features as human experts.
  • To assess the reliability and domain-groundedness of DNNs in medical image interpretation.

Main Methods:

  • Developed a framework comparing human and machine perception using perturbation robustness.
  • Mitigated Simpson's paradox through subgroup analysis for robust comparisons.
  • Applied the framework to a case study in breast cancer screening, analyzing microcalcifications and soft tissue lesions separately.

Main Results:

  • Inconclusive results regarding feature differences between humans and DNNs for microcalcification detection.
  • For soft tissue lesions, DNNs were found to rely on high-frequency image components disregarded by radiologists.
  • These high-frequency features identified by DNNs were located outside the regions of interest highlighted by radiologists.

Conclusions:

  • The study highlights significant differences in feature utilization between DNNs and human radiologists in breast cancer screening, particularly for soft tissue lesions.
  • DNNs may exploit high-frequency image components not typically used by human experts, potentially leading to diagnostic discrepancies.
  • The proposed framework, incorporating subgroup analysis and medical domain knowledge, is essential for uncovering these subtle but important differences between human and machine perception.